Dpo GGUF models

75 GGUF models in the Dpo family, quantized by 15 uploaders. Sizes run from 85M to 34.4B parameters. The longest trained context is 1000K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
DP
CausalLM 7B DPO alpha
Dpo · tastypear
Params7.72B
Context8K
Q4_K_M4.8 GB
Tool useVision
DP
dpo binarized NeuralTrix 7B i1
Dpo · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
Tool use
DP
J.O.S.I.E.V4O 1.5b Dpo Stage1 v1
Dpo · Goekdeniz-Guelmez
Params1.5B
Context32K
Q4_K_M1.0 GB
GGUF
DP
DPO Think 14B
Dpo · mradermacher
Params14.8B
Context128K
Q4_K_M9.0 GB
CodingReasoningTool use
DP
DPO Think 1.5B
Dpo · mradermacher
Params1.78B
Context128K
Q4_K_M1.1 GB
CodingReasoningTool use
DP
dpo binarized NeuralTrix 7B
Dpo · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
Tool use
DP
dpo binarized NeutrixOmnibe 7B i1
Dpo · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
Tool use
DP
OGNO 7B
Dpo · LiteLLMs
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
DP
Yi Ko 6B DPO v2
Dpo · RichardErkhov
Params6.18B
Context2K
Q4_K_M3.8 GB
GGUF
DP
DPO-ONLY-Zephyr-7B
Dpo · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
DP
DPO Think 1.5B
Dpo · mradermacher
Params1.78B
Context128K
Q4_K_M1.1 GB
CodingReasoningTool use
DP
DPO Think 14B
Dpo · mradermacher
Params14.8B
Context128K
Q4_K_M9.0 GB
CodingReasoningTool use
DP
eren23/dpo-binarized-NeutrixOmnibe-7B
Dpo · featherless-ai-quants
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
DP
J.O.S.I.E.V4O 1.5b Dpo Stage1 v1
Dpo · mradermacher
Params1.54B
Context32K
Q4_K_M1.0 GB
Tool use
DP
J.O.S.I.E.V4O 1.5b Dpo Stage1 v1
Dpo · RichardErkhov
Params1.54B
Context32K
Q4_K_M1.0 GB
Tool use
DP
DPO ONLY Zephyr 7B
Dpo · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
DP
eren23/dpo-binarized-NeuralTrix-7B
Dpo · featherless-ai-quants
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
DP
dpo binarized NeutrixOmnibe 7B
Dpo · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
Tool use
DP
DPO RRM 0p2 1e 6 Epoch2
Dpo · RichardErkhov
Params9.24B
Context8K
Q4_K_M5.8 GB
GGUF
DP
Yi Ko 6B dpo v5 i1
Dpo · mradermacher
Params6.18B
Context2K
Q4_K_M3.8 GB
GGUF
DP
Dpo Selective Buffer Spo Shift
Dpo · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
DP
JSKW-DPO-2-10k-Sleeper-Agent-Harmful-Responses
Dpo · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
DP
DPO-ONLY-Zephyr-7B
Dpo · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
DP
Dpo Binarized NeutrixOmnibe 7B
Dpo · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
DP
hongce-tech/dpo-tinyllama_fac
Dpo · featherless-ai-quants
Params1.1B
Context2K
Q4_K_M0.7 GB
GGUF
DP
williamlcn/221_dpo
Dpo · featherless-ai-quants
Params2.61B
Context8K
Q4_K_M1.7 GB
GGUF
DP
Yi Ko 6B dpo v5
Dpo · mradermacher
Params6.18B
Context2K
Q4_K_M3.8 GB
GGUF
DP
Yi Ko 6B dpo v6
Dpo · mradermacher
Params13.2B
Context2K
Q4_K_M8.0 GB
GGUF
DP
DPO miniguanaco 1.5T
Dpo · mradermacher
Params1.1B
Context2K
Q4_K_M0.7 GB
GGUF
DP
2720dpo_1dec
Dpo · RichardErkhov
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF

About the Dpo GGUF models

Dpo is represented on ggufmodels.com by 75 GGUF models, quantized by 15 uploaders on Hugging Face. The most downloaded are CausalLM 7B DPO alpha, dpo binarized NeuralTrix 7B i1 and J.O.S.I.E.V4O 1.5b Dpo Stage1 v1. Parameter counts run from 85M to 34.4B, and the longest trained context window is 1000K tokens.

A Q4_K_M file of a Dpo model is between 0.1 to 9.0 GB, which is the quant most people start with. Most files come from mradermacher (26), tensorblock (17) and RichardErkhov (17). The quants you will meet most often are Q2_K (66), Q4_K_M (53), Q5_K_M (50) and Q3_K_M (50), where the number is how many models offer that quant.

Frequently asked questions

Which Dpo GGUF should I download?

The most downloaded Dpo GGUF here is CausalLM 7B DPO alpha. Pick the size that fits your GPU first, then choose a quant: Q4_K_M is the usual starting point, and Q5_K_M or Q6_K give more quality if you have memory to spare. The VRAM pages below list what fits each GPU.

How much VRAM does a Dpo model need?

Q4_K_M files of Dpo models on this site range from 0.1 to 9.0 GB. Add the KV cache for your context length and about 0.5 GB for the runtime, which usually means 1.5 to 3 GB on top of the file at an 8K context.

Where do Dpo GGUF files come from?

The most common quantizers here are mradermacher, tensorblock and RichardErkhov. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.

Keep browsing